AI agents call video_analysis to retrieve information from Vison-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is designed for passive inspection and analysis of video content (local or remote), producing descriptive output. There is no indication it modifies, deletes, executes code, or performs financial operations. The 8MB file size limit and mention of 'describe' and 'detect' confirm read-only semantics typical of vision analysis tasks.
From the tool's definition Tool description states it "Inspect videos" and "describe scenes, detect events" — these are retrieval and analysis operations with no modification, deletion, or execution of external commands.
Attacks that exploit this kind of access
Inspect videos (local files ≤8MB, remote URLs) to describe scenes, detect events,. It is categorised as a Read tool in the Vison-MCP MCP Server, which means it retrieves data without modifying state.
Register the Vison- MCP server in PolicyLayer and add a rule for video_analysis: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Vison-MCP. Nothing to install.
video_analysis is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the video_analysis rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for video_analysis. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
video_analysis is provided by the Vison- MCP server (lin-zhibo/vison-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →